Skip to main content

Ilya Sutskever: Continuous vector representations for machine translation

Movies Preview

movies
Ilya Sutskever: Continuous vector representations for machine translation


Published February 12, 2014


Talk by Ilya Sutskever from Google. Given to the Redwood Center for Theoretical Neuroscience at UC Berkeley.

Abstract
Dictionaries and phrase tables are the basis of modern statistical machine translation systems. I will present a method that can automate the process of generating and extending dictionaries and phrase tables. Our method can translate missing word and phrase entries by learning language structures using large monolingual data, and by mapping between the languages using a small bilingual dataset. It uses distributed representations of words and learns a linear mapping between vector spaces of languages. Despite its simplicity, our method is surprisingly effective: we can achieve almost 90% precision@5 for translation of words between English and Spanish. This method makes little assumption about the languages, so it can be used to extend and refine dictionaries and translation tables for any language pairs. Joint work with Tomas Mikolov and Quoc Le.


Audio/Visual sound, color

comment
Reviews

There are no reviews yet. Be the first one to write a review.
SIMILAR ITEMS (based on metadata)
Community Video
movies
eye 1,117
favorite 0
comment 0
Arxiv.org
by Koichi Takeda
texts
eye 39
favorite 0
comment 0
Source: http://arxiv.org/abs/cmp-lg/9407008v1
Arxiv.org
by Carl Gold; Peter Sollich
texts
eye 23
favorite 0
comment 0
Source: http://arxiv.org/abs/cond-mat/0203334v1
Community Texts
by Mrs. Sangita B. Patil and Mr. Bapu K. Patil
texts
eye 44
favorite 0
comment 0
Arxiv.org
by Fabrice Rossi; Nathalie Villa
texts
eye 53
favorite 0
comment 0
Source: http://arxiv.org/abs/0705.0209v1
Arxiv.org
texts
eye 21
favorite 0
comment 0
Source: http://arxiv.org/abs/quant-ph/0701186v2
Community Video
movies
eye 225
favorite 0
comment 0
Arxiv.org
by Rogier Bos
texts
eye 17
favorite 0
comment 0
Source: http://arxiv.org/abs/math/0612639v3
Community Video
movies
eye 211
favorite 0
comment 0